The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using npx for project initialization (npx hyperframes init), skill management (npx skills add), and maintenance (npx hyperframes skills update). It also utilizes the gh CLI to read repository data. These commands are essential for the skill's operation and are part of the intended developer workflow.
[EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of remote code and configuration through its own CLI tools and the platform's skill installation mechanism. These resources are associated with the skill's author (heygen-com) and are used to pull specialized workflow skills on demand.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data from websites and GitHub Pull Requests.
Ingestion points: URLs crawled via headless Chrome and PR data fetched via the gh CLI.
Boundary markers: The instructions do not define specific delimiters or "ignore" warnings for the ingested data.
Capability inventory: The framework includes command execution (npx, gh) and network access (web crawling).
Sanitization: No explicit sanitization or validation of the external content is described in this routing skill.

hyperframes